Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 19151
    Prev
    Next
    INDEX
    Explanations

    words with a specific letter combination pattern and formatting

    oai_token-act-pair · gpt-3.5-turbo

    patterns in word structure and arrangement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grimes
    -0.95
    BuyableInstoreAndOnline
    -0.77
     Hayward
    -0.70
     Drake
    -0.69
    odynam
    -0.69
     Icar
    -0.69
     Kimber
    -0.67
     Pav
    -0.67
     FML
    -0.67
    Kin
    -0.66
    POSITIVE LOGITS
     parentheses
    1.42
     comma
    1.35
     conson
    1.32
     vowel
    1.30
     underscores
    1.28
     suffix
    1.27
     braces
    1.24
     subscript
    1.24
     letters
    1.24
     underscore
    1.21
    Activations Density 0.349%

    No Known Activations